Feedback
Settings

Settings

Goto Application

1. WO2022010855 - SYSTEMS, METHODS AND DEVICES FOR MAP-BASED OBJECT'S LOCALIZATION DEEP LEARNING AND OBJECT'S MOTION TRAJECTORIES ON GEOSPATIAL MAPS

Submit observation
PermaLink
Publication Number WO/2022/010855
Publication Date 13.01.2022
International Application No. PCT/US2021/040454
International Filing Date 06.07.2021
IPC
G01C 21/36 2006.1
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/-G01C19/104
26specially adapted for navigation in a road network
34Route searching; Route guidance
36Input/output arrangements for on-board computers
CPC
G01C 21/005
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
005with correlation of navigation data from several sources, e.g. map or contour matching
G01C 21/1652
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
10by using measurements of speed or acceleration
12executed aboard the object being navigated; Dead reckoning
16by integrating acceleration or speed, i.e. inertial navigation
165combined with non-inertial navigation instruments
1652with ranging devices, e.g. LIDAR or RADAR
G01C 21/1656
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
10by using measurements of speed or acceleration
12executed aboard the object being navigated; Dead reckoning
16by integrating acceleration or speed, i.e. inertial navigation
165combined with non-inertial navigation instruments
1656with passive imaging devices, e.g. cameras
G01C 21/30
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
26specially adapted for navigation in a road network
28with correlation of data from several navigational instruments
30Map- or contour-matching
G01C 21/3867
GPHYSICS
01MEASURING; TESTING
CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
21Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
38Electronic maps specially adapted for navigation; Updating thereof
3863Structures of map data
3867Geometry of map features, e.g. shape points, polygons or for simplified maps
Applicants
  • OHIO STATE INNOVATION FOUNDATION [US]/[US]
Inventors
  • YILMAZ, Alper
  • ZHA, Bing
Agents
  • WONG, Frankie Waitim
  • CHIN, JR., Davis M.
  • CHOU, Chia Yun
  • MEHTA, Manish
  • PRIBISICH, Risto
  • SCANLON, Stephen
  • SHOEMAKER, Debra
Priority Data
63/049,00507.07.2020US
63/064,65612.08.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEMS, METHODS AND DEVICES FOR MAP-BASED OBJECT'S LOCALIZATION DEEP LEARNING AND OBJECT'S MOTION TRAJECTORIES ON GEOSPATIAL MAPS
(FR) SYSTÈMES, PROCÉDÉS ET DISPOSITIFS D'APPRENTISSAGE PROFOND DE LOCALISATION D'OBJETS FONDÉ SUR UNE CARTE ET TRAJECTOIRES DE DÉPLACEMENT D'OBJETS SUR DES CARTES GÉOSPATIALES
front page image
Abstract
(EN) An object of initial unknown position on a map may be determined by traversing through moving and turning to establish motion trajectory to reduce its spatial uncertainty to a single location that would fit only to a certain map trajectory. A artificial neural network model learns from object motion on different map topologies may establish the object's end-to-end positioning from embedding map topologies and object motion. The proposed method includes learning potential motion patterns from the map and perform trajectory classification in the map's edge-space. Two different trajectory representations, namely angle representation and augmented angle representation (incorporates distance traversed) are considered and both a Graph Neural Network and an RNN are trained from the map for each representation to compare their performances. The results from the actual visual-inertial odometry have shown that the proposed approach is able to learn the map and localize the object based on its motion trajectories.
(FR) Un objet de position inconnue initiale sur une carte peut être déterminé par le parcours, le déplacement et la rotation afin d'établir une trajectoire de déplacement permettant de réduire son incertitude spatiale à un seul emplacement qui correspond uniquement à une certaine trajectoire de carte. Un modèle de réseau neuronal artificiel apprenant à partir d'un déplacement d'objet sur différentes topologies de carte peut établir le positionnement de bout en bout de l'objet à partir de topologies de carte d'intégration et d'un déplacement d'objet. Le procédé proposé consiste à apprendre des motifs de déplacement potentiels à partir de la carte et à réaliser une classification de trajectoire dans l'espace de bord de la carte. Deux représentations de trajectoires différentes, à savoir une représentation d'angle et une représentation d'angle augmentée (incorporant une distance parcourue) sont considérés et à la fois un réseau neuronal de graphe et un RNN sont entraînés à partir de la carte pour chaque représentation afin de comparer leurs performances. Les résultats de l'odométrie visuelle-inertielle réelle ont montré que l'approche proposée permet d'apprendre la carte et de localiser l'objet en fonction de ses trajectoires de déplacement.
Latest bibliographic data on file with the International Bureau
# -